© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 6431
    Prev
    Next
    INDEX
    Explanations

    comma followed by conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    3.53
    。
    2.70
    .[
    2.41
    .…
    2.37
    .;
    2.36
    .“
    2.34
    .:
    2.33
    .]
    2.29
    .​
    2.28
    .\\
    2.28
    POSITIVE LOGITS
     unsurprisingly
    2.20
     predictably
    2.11
     coupled
    2.05
     λοι
    2.05
     meanwhile
    2.01
    coupled
    2.00
     помимо
    1.99
     incidentally
    1.98
     understandably
    1.97
    however
    1.93
    Activations Density 0.225%

    No Known Activations